mcpbeat

Fractera MCP Server

io.github.Fractera/deploy
answering

Fractera is answering right now. Last checked 8 min ago. It exposes 8 tools.

Zero-Ops deploy of a private AI workspace to your own VPS — from your AI chat. Free and open-source.

Uptime history 40 hours of history
40 hours agonow
100.0%
Uptime 24h
91 of 91 checks
8
Tools
read from the server
328 ms
Response time
average over 24h
open, no key
Access
streamable-http

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 8 min ago.

run in your terminal
claude mcp add deploy --transport http https://www.fractera.ai/api/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "deploy": {
      "url": "https://www.fractera.ai/api/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.deploy]
url = "https://www.fractera.ai/api/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "deploy": {
      "url": "https://www.fractera.ai/api/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "deploy": {
      "url": "https://www.fractera.ai/api/mcp"
    }
  }
}

Available tools 8

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

development
get_ai_development_loop_info
Explains the Fractera development loop: how one admin request becomes tested, deployed, recorded code with no human writing it — Hermes orchestrates and loads its identity + project context, picks a ready coding agent (Claude Code, Codex, Gemini, Qwen, Kimi), the agent is enriched (SOUL.md / AGENTS.md / GLOSSARY.md / completed steps), generates a task then code, it is built and deployed, and the result branches (error feeds back; success updates the completed steps and the deployments tab) — all grounded by LightRAG memory at every step. RETURNS A DIAGRAM IMAGE URL you can show the user when they ask how Fractera builds software or how its agents work. Call with NO arguments to get the diagram URL + the "how the loop works" overview + the section list; call again with a single `section` id to read one stage in depth.
project
get_project_info
Project reference / help desk about Fractera. Use this to answer ANY user question about what Fractera is, how it works, its architecture, components, modes, data ownership, pricing, use cases, partner program, etc. — especially while a deploy is running and the user wants to learn more. TOKEN-ECONOMY: call with NO arguments first to get the lightweight list of section ids+titles, then call again with a single `section` id to fetch just that section. NEVER try to fetch everything at once; pull only the section(s) relevant to the user question. Set `lang:"ru"` for Russian-speaking users.
register
register_and_deploy
Register a new Fractera user and start the deployment of their server in one atomic call. Use this AFTER you have collected the user's email (entered twice for typo protection), server IP, and root password. Creates the User row (or reuses an existing one with the same email), creates a free Subscription, creates a ServerToken, wipes any previous installation on the target server, and launches bootstrap. The deploy is IP-first (phase-1): the server comes up on plain HTTP at http://<IP>:3002 in 8-14 minutes; it does NOT get a domain or HTTPS cert here (that is an optional later step inside the workspace). Returns session_id (for a single on-demand check_status read — do not poll) and server_token (so the user can recover via retry_deploy if anything breaks). Call this AT MOST ONCE per conversation.
retry
retry_deploy
Retry a failed deployment using a server_token (from the failure email, the deploy-progress UI, or the dashboard). Wipes the previous broken install and runs a fresh deploy on the SAME server. Returns a new session_id — poll with check_status. Use this when the user reports a failed deploy or pastes a server_token.
status
check_status
Read the current installation progress ONCE, on demand. Call this only when the user explicitly asks how the deploy is going (e.g. "what is the status", "did it finish") — never on a timer and never in a polling loop. The deploy takes 8-14 minutes and the authoritative status channels are the email pipeline + the dashboard; one read on request is enough. Returns the current step, the list of completed steps (~44 total in a full bootstrap), and whether installation is done or failed.
subdomain
get_subdomain
Return the final entry address of the server once installation is complete. In phase-1 (IP-first) this is a plain-HTTP Admin URL of the form http://<IP>:3002 — the server has NO domain and NO HTTPS cert yet (attaching a custom domain with HTTPS is an optional later step the user does inside Admin -> Personal Domain). Call this once after check_status reports status="done".
vps
get_vps_recommendation
Return a single recommended VPS provider for users who do not yet have a server. Call this ONLY when the user explicitly says they have no server. The user buys the VPS at this provider and comes back with IP + password.
workspace
get_ai_workspace_architect_info
Architecture reference for Fractera AI Workspace: what it is made of and how it works (the admin drives it through Hermes — chat Web UI or Telegram — or directly through the five coding agents; a modal subscription sign-in layer + MCP keep work resilient when a subscription is limited; LightRAG is the central memory that slashes token use; Hermes is a light orchestrator while the coding agents do the heavy lifting; the result ships over HTTPS on a custom domain or plain HTTP on an IP). RETURNS A DIAGRAM IMAGE URL you can show the user when they ask what Fractera is or how it works. Call with NO arguments to get the wide illustration URL + the core "how it works" scenario + the section list; call again with a single `section` id to read one entity in depth.

Endpoints

URLTransportStateLatencyChecked
https://www.fractera.ai/api/mcp streamable-http answering 316 ms 8 min ago

Fractera — questions

Answers built from our own checks of this server.

What can Fractera do?
It exposes 8 tools, read directly from the server on our last check. Among them: check_status, get_ai_development_loop_info, get_ai_workspace_architect_info, get_project_info, get_subdomain, get_vps_recommendation and 2 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Fractera working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 328 ms. The bar chart above shows every period we have measured.
How do I connect Fractera?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Fractera need an API key?
No. Fractera completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 8 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Fractera?
It answers our handshake in 328 ms on average, which is faster than 43% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.